{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40877920", "kind": "science-record", "revision": 2, "content_hash": "sha256:82cf32a66783b5d1ad7c13179684f2e99d7e662d12a64422c859ea07b25cac63", "created_at": "2026-11-01T10:25:52Z", "updated_at": "2026-11-01T14:01:47Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Construction of lactylation (LA) risk signature in prostate cancer based on 4D fast DIA L-lactated quantitative genomics.", "doi": "10.1186/s12967-025-06990-6", "pmid": "40877920", "authors": null, "journal": "Journal of translational medicine", "year": 2025, "abstract": null, "claims": [{"id": "claim-1", "statement": "the headline numerical result the paper states for its main finding", "kind": "quantitative", "state": "complete", "target": {"value": 122.0, "unit": "degs", "tolerance": null, "source": "chars 1420-1485 of source sha256 48d6310e590bcbf746861e05977ec4e1b26c75656365075305bcda316e89eb7a"}, "evidence": [{"asset": "source:pmid:40877920", "locator": "chars 1420-1485 of source sha256 48d6310e590bcbf746861e05977ec4e1b26c75656365075305bcda316e89eb7a", "quote": "A total of 122 DEGs were screened to construct a gene risk model."}]}], "gaps": ["abstract", "authors"]}, "experiment": {"state": "partial", "objective": "the headline numerical result the paper states for its main finding", "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate and its interval from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The number a replication must land on, and the sentence it came from.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:40877920"], "outputs": ["the published estimate, its unit and its interval"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data behind the published result", "kind": "data-preparation", "state": "blocked", "blocked_on": "data:not_downloaded", "description": "The published result cannot be recomputed without the data the paper analysed.", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the source data with its provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the analysis programme", "kind": "analysis", "state": "blocked", "blocked_on": "no owned computational capability is bound to this experiment", "description": "Re-run the paper's analysis on the source data and produce the registered result. | SEP input not carried into the asset list: materials:the source data behind the published result in pmid:40877920", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the registered result"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:not_downloaded", "step:run_analysis blocked on no owned computational capability is bound to this experiment", "step:run_analysis input 'materials:the source data behind the published result in pmid:40877920' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40877920", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s12967-025-06990-6", "sha256": "sha256:48d6310e590bcbf746861e05977ec4e1b26c75656365075305bcda316e89eb7a", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s12967-025-06990-6", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:40877920:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:8fe4cb6599879efe2d85db4b99609ad208ee3fa39c551c9e579330adb3f76d02", "bytes": 930, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#Tab1", "version": null, "note": "The antibodies used in this study and their specific applications", "structure": {"pmcid": "PMC12392559", "section_index": 10, "section_title": "Immunohistochemistry", "row_count": 12, "column_count": 4}, "table": {"label": "Table 1", "caption": "The antibodies used in this study and their specific applications", "rows": [["ID", "Brand", "Product number", "Application"], ["anti-KCNMA1", "Santa Cruz", "sc-374,142", "1:500 for WB,1:200 for IHC,1:10 for IP"], ["anti-H3K18la", "PTM-Bio", "PTM-1406RM", "1:1000 for WB"], ["anti-β-tubulin", "Proteintech", "10094-1-AP", "1:10000 for WB"], ["anti-GAPDH", "Proteintech", "10494-1-AP", "1:10000 for WB"], ["anti-KI67", "Proteintech", "27309-1-AP", "1:200 for IF"], ["anti-ERK", "PTM-Bio", "PTM-6324", "1:2000 for WB"], ["anti-P-ERK", "Proteintech", "28733-1-AP", "1:2000 for WB,1:100 for IF"], ["anti-MEK", "Proteintech", "11049-1-AP", "1:5000 for WB"], ["anti-P-MEK", "Cell Signaling Technology", "# 9154", "1:1000 for WB"], ["anti-RAF", "Abcam", "ab200653", "1:1000 for WB"], ["anti-RAS", "Proteintech", "12063-1-AP", "1:10000 for WB"]], "row_count": 12, "column_count": 4, "numeric_cells": 24, "header_rows": 1, "locator": "section[10]/table-wrap[1]#Tab1"}}], "gaps": ["asset:source:pmid:40877920 not verified"]}, "analysis": {"state": "absent", "methods": [], "targets": [], "gaps": ["method", "targets"]}, "capability": {"state": "absent", "requirements": [], "gaps": ["capability"]}, "readiness": {"state": "partial", "tier": null, "blocking_axis": null, "blocked_on": null, "axes": {}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:40877920", "asset:table:pmid:40877920:1"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:40877920"]}, "gaps": ["corpus_record_absent"]}, "review": {"state": "partial", "machine_critique": {"status": "blocked", "providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "full-text-reading-v1", "prompt_hash": "7e61bf48e5d50213f766140eecab3bc32f5d257c6be4cdbcc4d4de846797429f", "source_hash": "48d6310e590bcbf746861e05977ec4e1b26c75656365075305bcda316e89eb7a", "raw_response_sha256": "sha256:d918a6922daf0a409e75dd81502db288a8c2c0c603e58cd0ab6eb4167d59cd84", "raw_response_chars": 5606}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "bc1081ff8c55ec291d74e2845b784e6338515491829dedbfca789c8537e5d2c7", "source_hash": "48d6310e590bcbf746861e05977ec4e1b26c75656365075305bcda316e89eb7a", "raw_response_sha256": "sha256:ad1ab1ccc1b9a69211d02cc71bb49cb0a1e5c9153b3eb91bf1f21df28ac00d77", "raw_response_chars": 55587}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "2838d66eafd37a0b9e0d17e2a8280f34ac976b724e492ed13710a4df7910b5ba", "source_hash": "48d6310e590bcbf746861e05977ec4e1b26c75656365075305bcda316e89eb7a", "raw_response": "{\"parent_value\":122,\"unit\":\"DEGs\",\"evidence\":\"A total of 122 DEGs were screened to construct a gene risk model.\",\"target_result\":\"The paper states that 122 differentially expressed genes were screened to construct the lactylation-related gene risk model.\",\"number_stated\":true}", "reading": {"parent_value": 122, "unit": "DEGs", "evidence": "A total of 122 DEGs were screened to construct a gene risk model.", "target_result": "The paper states that 122 differentially expressed genes were screened to construct the lactylation-related gene risk model.", "number_stated": true, "source_locator": "chars 1420-1485 of source sha256 48d6310e590bcbf746861e05977ec4e1b26c75656365075305bcda316e89eb7a"}, "recorded_at": "2026-10-31T15:33:14.635153+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "f673567c716ea00045ec3d1e7c1f20d57c5524dcfb6513e2c0e6688386376804", "source_hash": "48d6310e590bcbf746861e05977ec4e1b26c75656365075305bcda316e89eb7a", "raw_response": "<think>We need answer JSON only. Need identify single numerical result headline main finding registered target. Source is abstract/results. Numerical candidates: total 122 DEGs screened to construct gene risk model; K-M p values test 0.025 training &lt;0.001. Main headline perhaps 122 DEGs? User wording \"headline numerical result the paper itself states for its main finding.\" Need infer target likely asks replication of registered target headline numerical result. Need report value paper states. The abstract's main finding includes \"A total of 122 DEGs were screened to construct a gene risk model.\" Is that headline number? Could be. Need exact contiguous quote containing number and attribution whole clause. Unit perhaps \"DEGs\" or \"differentially expressed genes\" or empty? Number 122 and unit \"DEGs\". Evidence exact quote: \"A total of 122 DEGs were screened to construct a gene risk model.\" This states numerical result. Target main finding is LA risk model. Maybe p values are validation statistical results, but \"headline numerical result\" perhaps 122 DEGs. Need understand instruction likely benchmark extraction. Registered target generic. They expect numerical result in abstract. Could select 122 DEGs because prominent and tied to model. Let's parse.\n\nQuestion: \"Read the supplied paper text and find the single numerical result that a replication of the registered target has to reproduce. Report the headline number only: the value the paper itself states for the registered target, not a value you calculated, converted, averaged or reconstructed. The unit must be the unit the paper prints. The evidence must be an exact, contiguous quotation from SOURCE TEXT that contains the number; do not shorten it, do not add an ellipsis and do not paraphrase it. Attribution may be carried by the text's own wording: a number may be attached to the target by a parenthetical list, by the word 'respectively', or by words that name the target directly. When that is how the text links them, quote the whole clause so a reader can check the attribution for themselves. If the text states no number for the registered target, set number_stated to false, leave parent_value at 0, leave unit and evidence empty, and say in target_result what the text does state instead.\"\n\nRegistered target: \"the headline numerical result the paper itself states for its main finding\". We need identify. Abstract result says total 122 DEGs, p-values, etc. Which is \"headline numerical result\"? Probably 122 DEGs. Could also be P values of KM: test group 0.025 and training group &lt;0.001 (two numbers, contrary \"single numerical result\"). \"Single\" may point to 122. The paper title 4D fast DIA L-lactated quantitative genomics; maybe headline result is \"A total of 122 DEGs...\" in results. Need report unit paper prints: DEGs. Could unit perhaps \"DEGs\" exactly. Parent_value 122. Evidence exact sentence. target_result perhaps description. number_stated true.\n\nNeed JSON valid no extra. What should target_result say? Probably \"122 DEGs were screened to construct the LA risk model.\" Since headline number. We can put that. Evidence exact contiguous. Ensure quote not add. Unit \"DEGs\". Is \"unit\" count of DEGs. Could use \"DEGs\". Let's ensure no ambiguity.\n\nMaybe main numerical result is P = 0.025 test group / P &lt; 0.001 training cohort, but asks single numerical result perhaps registered target itself could have one headline metric such as AUC usually. Here no AUC number. There are many method parameters. Only headline model-related count is 122 DEGs. Yes.\n\nCould unit be \"DEGs\" or \"genes\"? Paper prints \"122 DEGs\". User says unit must be unit paper prints. \"DEGs\" is printed. Use \"DEGs\". Evidence exact.\n\ntarget_result maybe \"A total of 122 DEGs were screened to construct a gene risk model.\" Exact? Could repeat quote. Fine.\n\nLet's answer only JSON object.</think>\n\n{\"parent_value\":122,\"unit\":\"DEGs\",\"evidence\":\"A total of 122 DEGs were screened to construct a gene risk model.\",\"target_result\":\"A total of 122 DEGs were screened to construct the LA risk model.\",\"number_stated\":true}", "reading": {"parent_value": 122, "unit": "DEGs", "evidence": "A total of 122 DEGs were screened to construct a gene risk model.", "target_result": "A total of 122 DEGs were screened to construct the LA risk model.", "number_stated": true, "source_locator": "chars 1420-1485 of source sha256 48d6310e590bcbf746861e05977ec4e1b26c75656365075305bcda316e89eb7a"}, "recorded_at": "2026-10-31T15:33:19.257584+00:00"}], "agreement": false, "disagreements": {"target_result": {"minimax": "A total of 122 DEGs were screened to construct a gene risk model.", "minimax_alt": "The K-M curves verified the differences between the high - and low - risk groups of the model in the test group and the training cohort (test group: P = 0.025; training group: P < 0.001).", "decisive": false}, "physical_methods": {"minimax": ["quantitative lactylation proteomics", "LC-MS/MS analysis", "Western blot analysis", "in vitro experiments", "animal experiments"], "minimax_alt": ["quantitative lactylation proteomics of human prostate cancer tissues", "LC-MS/MS analysis using timsTOF Pro2 mass spectrometry in dia-PASEF mode", "Western blot analysis", "in vitro prostate cancer cell experiments", "animal tumor experiments"], "decisive": false}, "analysis_methods": {"minimax": ["ConsensusCluster Plus consensus unsupervised clustering analysis", "Principal component analysis (PCA)", "differential expression analysis", "Lasso-Cox regression analysis", "K-M curves", "receiver operating characteristic (ROC) curves", "nomograms", "chi-square test", "stratification analysis", "Gene Ontology enrichment analysis", "KEGG pathway enrichment analysis", "ESTIMATE", "CIBERSORT", "IOBR"], "minimax_alt": ["consensus unsupervised clustering analysis using ConsensusClusterPlus", "Principal component analysis (PCA)", "identification of differentially expressed genes (DEGs)", "Lasso-Cox regression analysis", "K-M curves", "receiver operating characteristic (ROC) curves", "nomograms", "chi-square test", "ESTIMATE", "CIBERSORT", "IOBR", "gene set enrichment analysis", "GO and KEGG pathway enrichment analysis", "one-way ANOVA", "scRNA-seq analysis using TISCH2"], "decisive": false}, "statistical_method": {"minimax": "Lasso-Cox regression analysis", "minimax_alt": "K-M curves", "decisive": true}}, "agreement_basis": {"policy": "decisive_fields", "decisive_fields": ["work_type", "number_stated", "parent_value", "unit"]}, "blinded": true}, "human_critique": {"status": "not_run", "reviewer": null, "signed_at": null, "conflict_checked": false, "commentary": null}, "stages": [{"key": "target_materials", "status": "pending", "reason": null, "evidence": null}, {"key": "independent_readings", "status": "blocked", "reason": "The independent readings are incomplete or disagree; the source evidence must resolve the difference.", "evidence": {"provider_errors": []}}, {"key": "source_resolution", "status": "pending", "reason": null, "evidence": null}, {"key": "protocol_reconstruction", "status": "pending", "reason": null, "evidence": null}, {"key": "control_execution", "status": "pending", "reason": null, "evidence": null}, {"key": "control_comparison", "status": "pending", "reason": null, "evidence": null}, {"key": "publication", "status": "pending", "reason": null, "evidence": null}], "gaps": ["review.human_critique", "review.machine_critique.blocked"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "package:096a4d403b5619732ca04b48dae71bf9ef8da39550467fff216438f582202e82", "type": "sep_package", "label": "SEP v1 package for pmid:40877920"}], "activities": [{"id": "activity:conversion:pmid:40877920", "type": "conversion", "used": ["package:096a4d403b5619732ca04b48dae71bf9ef8da39550467fff216438f582202e82"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:minimax", "type": "model", "label": "minimax"}, {"id": "agent:minimax_alt", "type": "model", "label": "minimax_alt"}, {"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}], "source_run_id": "run-20261023T122449232913", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "pmid:40877920", "parent_hash": "sha256:36fd99e6a4e53eaa3adef6d121d8e64631bd77cbc35f45034bbc677705b6dbe6", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:40877920 not verified", "authors", "capability", "corpus_record_absent", "execution.not_run", "method", "review.human_critique", "review.machine_critique.blocked", "step:obtain_source_data blocked on data:not_downloaded", "step:run_analysis blocked on no owned computational capability is bound to this experiment", "step:run_analysis input 'materials:the source data behind the published result in pmid:40877920' does not resolve to a declared asset", "targets"]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T02:48:26+00:00","total_papers":5529,"total_assays_tracked":29,"automatable_assay_families":6,"validated":true,"caveat_count":9,"blocking_caveats":5,"caveats":[{"code":"low_evidence_dominates","basis":["4,152 of 5,529 classifications (75.1%) matched no cue evidence and sit at the 0.05 floor.","34 of 230 data_only calls (14.8%) are in that group."],"claim":"Work type and confidence bands","gloss":"Most records were classified from their title and framing alone, with assay-cue coverage at zero.","detail":"Most classifications in this run rest on no matched evidence at all. At the evidence floor the work type comes from title framing and a fixed prior, not from anything in the paper, so the published work-type split should be read as a rough triage signal rather than a measured distribution. The impact is bounded but not removed: since 2026-10-23 the engine excludes floor-confidence records from the shortlist entirely and publishes them separately as held out, so the recommendation is unaffected even though the census is.","status":"unverified","severity":"high"},{"code":"runtime_is_modelled","basis":["Runtime is summed from published per-assay hour figures. Timing awaits the first executed replication.","4,407 of 5,529 records (79.7%) model to 0.00 hours because no assay was matched, which the ranking then reads as \"cheapest\".","0 of 10 shortlisted records carry a 0.00-hour estimate."],"claim":"Estimated replication runtime","gloss":"The hour figures are estimates built from assay mentions; timing awaits the first executed replication.","detail":"The hour figures are a cost model derived from the bench steps implied by each matched assay family. The first executed replication will supply measured timing. Records without an assay match currently receive a zero-hour model value.","status":"unverified","severity":"high"},{"code":"signal_score_without_citations","basis":["5,529 of 5,529 records (100.0%) have no citation count from the source metadata."],"claim":"Signal score","gloss":"The signal score uses publication-type weight because the mirror supplied zero citation counts.","detail":"The source supplied no citation counts for any record in this run, so the signal score is publication-type weight only. The citation term of the ranking is inert here, and the shortlist is ordered by publication type alone.","status":"unverified","severity":"high"},{"code":"abstract_absent","basis":["1,667 of 5,529 records (30.2%) carry no abstract at all."],"claim":"Evidence base for classification","gloss":"Some records contain a title and publication type only, defining the available classification evidence.","detail":"Where the mirror contains a title and publication types only, those fields define the classifier evidence. A methods section is required for fuller automated and human review.","status":"unverified","severity":"medium"},{"code":"classifier_agreement_measured","basis":["Published two-way decision agreement 77.7% (310 of 399 decidable records) from a stratified hand-check of 438 real records.","Three-way diagnostic agreement 73.9% (288 of 390 decidable records).","data_only agreement 75.2% (100 of 133 decidable).","48 record(s) could not be decided from title and abstract and were excluded from the denominator.","56 analysis-only records were published under another work type, so the data_only share is not an upper bound."],"claim":"Published automatable decision","gloss":"This figure has been checked against a human reading the same papers, so we know how often it is right.","detail":"The published automatable / not-automatable distribution comes from a rule-based classifier that was hand-checked against a fixed ground-truth definition. The agreement rates below are measured, not estimated. The three-way work type remains a diagnostic and is reported separately.","status":"measured","severity":"high"},{"code":"llm_comparison_not_measured","basis":["rule_based_v1+lex99e1195c7d6f produced 5,529 of 5,529 classifications.","Measured on 438 labelled records; these are RULE-BASED figures, not model results."],"claim":"Rule-based versus LLM agreement","gloss":"Every number here is the rule engine’s own. Model comparison begins when a working API credential is connected and measured.","detail":"The published two-way decision agreed with a human reading on 310 of 399 decidable records (77.7%). The diagnostic three-way label agreed on 288 of 390 decidable records (73.9%). Every percentage in this run belongs to the rule engine. Model comparison begins when a working API credential is connected and measured.","status":"not_measured","severity":"high"},{"code":"confidence_is_a_band","basis":["low band: 135 of 210 hand-judged records were correct, 64.3% [57.6, 70.5] (95% CI).","medium band: 80 of 104 hand-judged records were correct, 76.9% [68.0, 84.0] (95% CI).","high band: 73 of 76 hand-judged records were correct, 96.0% [89.0, 98.7] (95% CI).","A fitted calibrated probability was built, measured and withdrawn: it overstated held-out accuracy and reorders nothing."],"claim":"Confidence band and evidence score","gloss":"The confidence band carries a measured accuracy interval; 0.85 represents relative rank strength.","detail":"Confidence on this run is a BAND plus its measured accuracy interval. The number stored alongside each record is a monotone evidence score that orders records; 0.85 represents relative rank strength. A fitted probability was withdrawn after it overstated held-out accuracy. Threshold on the band.","status":"measured","severity":"medium"},{"code":"three_way_split_is_diagnostic","basis":["The corpus is published at the two-way decision: automatable or not-automatable. The three-way split (data_only / physical / mixed) is published as a diagnostic with its measured reliability attached, not as a claim, because the rule engine's `mixed` call cannot be defended.","The engine called 22 record(s) mixed; 10 matched the human judgement (45.5%, 95% CI 26.9-65.3).","The engine's `mixed` call is right on 10/22 hand-judged records (45.5%, 95% CI 26.9%-65.3%); a constant `physical` guess scores 36.4%.","The engine's `mixed` call does not reliably beat a constant `physical` guess on the hand-judged records it labels mixed.","The sign of that difference flips between two independent samples, so the three-way refinement is not demonstrably informative.","The mixed stratum contributes a disproportionate share of errors relative to its size.","At title-only depth the physical/mixed split collapses: a title says that work was done, not whether it was also analysed."],"claim":"The published decision is two-way","gloss":"The three-way split is shown for diagnosis only. The published split is two ways.","detail":"Count and filter the corpus on automatable versus not-automatable. The data_only / physical / mixed split remains an internal engine diagnostic because the mixed call has lower measured reliability.","status":"measured","severity":"medium"},{"code":"automatable_flag_unproven","basis":["6 of 29 assay families are marked automatable now: meta_analysis, machine_learning, survival_analysis, pca, molecular_docking, differential_expression.","The flag is a rule over assay family and work type; validation begins with the first executed replication.","It inherits the 75.2% data_only agreement rate, because the flag requires the record to be analysis-only."],"claim":"Automatable now","gloss":"This flag marks assay families the rules classify as data-only. The first executed replication will validate it.","detail":"This flag marks families the rules consider replicable from data alone. Its validity depends on the analysis-only classification and will be measured through an executed replication.","status":"unverified","severity":"medium"}],"confidence_policy":"band_with_measured_interval","confidence_contract":{"policy":"band_with_measured_interval","summary":"Confidence is reported as a BAND with a measured accuracy interval. The raw evidence score supplies monotone ordering. A fitted point estimate was withdrawn after it overstated held-out accuracy.","evidence_score":"A monotone evidence score in [0,1] built from cue mass, axis separation and text coverage. Use it to order records. Interpret 0.85 as relative rank strength.","confidence_band":"low | medium | high. Consumers threshold on this value.","band_accuracy":"Wilson 95% interval on the measured agreement of the hand-judged records in this band.","calibrated_confidence":"WITHDRAWN. Reintroduction requires held-out evidence demonstrating reliable estimates across every bin."},"band_accuracy":{"low":{"n":210,"low":0.576,"band":"low","high":0.7046,"agree":135,"accuracy":0.6429},"high":{"n":76,"low":0.8903,"band":"high","high":0.9865,"agree":73,"accuracy":0.9605},"medium":{"n":104,"low":0.6795,"band":"medium","high":0.8397,"agree":80,"accuracy":0.7692}},"provider":"rule_based_v1+lex99e1195c7d6f","lexicon_id":"99e1195c7d6f","contract_published_at":"2026-10-23T12:25:29.022232+00:00","confidence_is_band":true,"confidence_is_probability":false,"decision_taxonomy":"two_way","decidable_fraction_two_way":0.8854,"decidable_fraction_two_way_low":0.8565,"decidable_fraction_two_way_high":0.9143,"decidable_fraction_three_way":0.8586,"decidable_fraction_three_way_low":0.8287,"decidable_fraction_three_way_high":0.8884,"decidable_population":5529,"validation_sample_size":438,"three_way_cost_fraction":0.0268,"three_way_cost_records":148,"decision_counts":{"automatable":230,"not_automatable":5299},"decision_split":{"automatable":{"count":230,"share":0.04159884246699222},"not_automatable":{"count":5299,"share":0.9584011575330078}},"diagnostic_work_type_counts":{"mixed":24,"physical":5275,"data_only":230}}}